Value of Contrast-Enhanced Ultrasound in Adjusting the Classification of Chinese-TIRADS 4 Nodules

Predictive Value of the Nomogram Model Based on Multimodal Ultrasound Features for Benign and Malignant Thyroid Nodules of C-TIRADS Category 4

To explore the predictive value of the nomogram model based on multimodal ultrasound features for benign and malignant thyroid nodules of C-TIRADS category 4. A retrospective analysis was conducted on the general conditions and ultrasound features of patients who underwent thyroid ultrasound examination and fine needle aspiration biopsy (FNA) or thyroidectomy at the Affiliated Hospital of Zunyi Medical University from April 2020 to April 2023. Predictive signs for benign and malignant nodules of thyroid C-TIRADS category 4 were screened through LASSO regression and multivariate logistic regression analysis to construct a nomogram prediction model. The predictive efficiency and accuracy of the model were assessed through ROC curves and calibration curves. Seven independent risk factors in the predictive model for benign and malignant thyroid nodules of C-TIRADS category 4 were growth pattern, morphology, microcalcifications, SR, arterial phase enhancement intensity, initial perfusion time, and PE [%]. Based on these features, the area under the curve (AUC) of the constructed prediction model was 0.971 (p ＜ .001, 95% CI: 0.952-0.989), with a prediction accuracy of 93.1%. Internal validation showed that the nomogram calibration curve was consistent with reality, and the decision curve analysis indicated that the model has high clinical application value. The nomogram prediction model constructed based on the multimodal ultrasound features of thyroid nodules of C-TIRADS category 4 has high clinical application value.

Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames

Objectives

To apply machine learning to extract radiomics features from thyroid two-dimensional ultrasound (2D-US) combined with contrast-enhanced ultrasound (CEUS) images to classify and predict benign and malignant thyroid nodules, classified according to the Chinese version of the thyroid imaging reporting and data system (C-TIRADS) as category 4.

Materials and methods

This retrospective study included 313 pathologically diagnosed thyroid nodules (203 malignant and 110 benign). Two 2D-US images and five CEUS key frames ("2nd second after the arrival time" frame, "time to peak" frame, "2nd second after peak" frame, "first-flash" frame, and "second-flash" frame) were selected to manually label the region of interest using the "Labelme" tool. A total of 7 images of each nodule and their annotates were imported into the Darwin Research Platform for radiomics analysis. The datasets were randomly split into training and test cohorts in a 9:1 ratio. Six classifiers, namely, support vector machine, logistic regression, decision tree, random forest (RF), gradient boosting decision tree and extreme gradient boosting, were used to construct and test the models. Performance was evaluated using a receiver operating characteristic curve analysis. The area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), and F1-score were calculated. One junior radiologist and one senior radiologist reviewed the 2D-US image and CEUS videos of each nodule and made a diagnosis. We then compared their AUC and ACC with those of our best model.

Results

The AUC of the diagnosis of US, CEUS and US combined CEUS by junior radiologist and senior radiologist were 0.755, 0.750, 0.784, 0.800, 0.873, 0.890, respectively. The RF classifier performed better than the other five, with an AUC of 1 for the training cohort and 0.94 (95% confidence interval 0.88-1) for the test cohort. The sensitivity, specificity, accuracy, PPV, NPV, and F1-score of the RF model in the test cohort were 0.82, 0.93, 0.90, 0.85, 0.92, and 0.84, respectively. The RF model with 2D-US combined with CEUS key frames achieved equivalent performance as the senior radiologist (AUC: 0.94 vs. 0.92, P = 0.798; ACC: 0.90 vs. 0.92) and outperformed the junior radiologist (AUC: 0.94 vs. 0.80, P = 0.039, ACC: 0.90 vs. 0.81) in the test cohort.

Conclusions

Our model, based on 2D-US and CEUS key frames radiomics features, had good diagnostic efficacy for thyroid nodules, which are classified as C-TIRADS 4. It shows promising potential in assisting less experienced junior radiologists.

Diagnostic value of CEUS combined with C-TIRADS for indeterminate FNA cytological thyroid nodules

OBJECTIVES

To investigate the diagnostic value of CEUS combined with C-TIRADS for indeterminate FNA cytological thyroid nodules.

METHODS

The clinical data, ultrasonic images, C-TIRADS categories and CEUS images of 192 patients with indeterminate FNA cytological thyroid nodules confirmed by the surgical pathology were analyzed retrospectively. The diagnostic efficacy of CEUS, C-TIRADS and CEUS-TIRADS were calculated.

RESULTS

The AUCs of CEUS, C-TIRADS and CEUS-TIRADS were 0.905 (95% CI: 0.862∼0.949), 0.881 (95% CI: 0.825∼0.938) and 0.954 (95% CI: 0.922∼0.986), respectively. The sensitivity, specificity, PPV, NPV, accuracy, LR- and LR+ were 84.7% (116/137), 85.5% (47/55), 93.5% (116/124), 69.1% (47/68), 84.9% (163/192), 0.179, 5.82 and 84.7% (116/137), 83.6% (46/55), 92.8% (116/125), 68.7% (46/67), 84.4% (162/192), 0.183, 5.17, 92.7% (127/137), 89.1% (49/55), 95.5% (127/133), 83.1% (49/59), 91.7% (176/192), 0.082, and 8.50, respectively. Compared with CEUS and C-TIRADS, CEUS-TIRADS had improved the AUC, sensitivity and accuracy (all P < 0.05).

CONCLUSIONS

CEUS and C-TIRADS had high diagnostic values in indeterminate FNA cytological thyroid nodules. CEUS-TIRADS improved AUC, diagnostic sensitivity and accuracy, and helped to distinguish indeterminate FNA cytological nodules.

Diagnostic efficiency among Eu-/C-/ACR-TIRADS and S-Detect for thyroid nodules: a systematic review and network meta-analysis

Background

The performance in evaluating thyroid nodules on ultrasound varies across different risk stratification systems, leading to inconsistency and uncertainty regarding diagnostic sensitivity, specificity, and accuracy.

Objective

Comparing diagnostic performance of detecting thyroid cancer among distinct ultrasound risk stratification systems proposed in the last five years.

Evidence acquisition

Systematic search was conducted on PubMed, EMBASE, and Web of Science databases to find relevant research up to December 8, 2022, whose study contents contained elucidation of diagnostic performance of any one of the above ultrasound risk stratification systems (European Thyroid Imaging Reporting and Data System[Eu-TIRADS]; American College of Radiology TIRADS [ACR TIRADS]; Chinese version of TIRADS [C-TIRADS]; Computer-aided diagnosis system based on deep learning [S-Detect]). Based on golden diagnostic standard in histopathology and cytology, single meta-analysis was performed to obtain the optimal cut-off value for each system, and then network meta-analysis was conducted on the best risk stratification category in each system.

Evidence synthesis

This network meta-analysis included 88 studies with a total of 59,304 nodules. The most accurate risk category thresholds were TR5 for Eu-TIRADS, TR5 for ACR TIRADS, TR4b and above for C-TIRADS, and possible malignancy for S-Detect. At the best thresholds, sensitivity of these systems ranged from 68% to 82% and specificity ranged from 71% to 81%. It identified the highest sensitivity for C-TIRADS TR4b and the highest specificity for ACR TIRADS TR5. However, sensitivity for ACR TIRADS TR5 was the lowest. The diagnostic odds ratio (DOR) and area under curve (AUC) were ranked first in C-TIRADS.

Conclusion

Among four ultrasound risk stratification options, this systemic review preliminarily proved that C-TIRADS possessed favorable diagnostic performance for thyroid nodules.

Systematic review registration

https://www.crd.york.ac.uk/prospero, CRD42022382818.

The diagnostic value of a nomogram based on multimodal ultrasonography for thyroid-nodule differentiation: A multicenter study

Objective

To establish and verify a nomogram based on multimodal ultrasonography (US) for the assessment of the malignancy risk of thyroid nodules and to explore its value in distinguishing benign from malignant thyroid nodules.

Methods

From September 2020 to December 2021, the data of 447 individuals with thyroid nodules were retrieved from the multicenter database of medical images of the National Health Commission’s Capacity Building and Continuing Education Center, which includes data from more than 20 hospitals. All patients underwent contrast-enhanced US (CEUS) and elastography before surgery or fine needle aspiration. The training set consisted of three hundred datasets from the multicenter database (excluding Zhejiang Cancer Hospital), and the external validation set consisted of 147 datasets from Zhejiang Cancer Hospital. As per the pathological results, the training set was separated into benign and malignant groups. The characteristics of the lesions in the two groups were analyzed and compared using conventional US, CEUS, and elastography score. Using multivariate logistic regression to screen independent predictive risk indicators, then a nomogram for risk assessment of malignant thyroid nodules was created. The diagnostic performance of the nomogram was assessed utilizing calibration curves and receiver operating characteristic (ROC) from the training and validation cohorts. The nomogram and The American College of Radiology Thyroid Imaging, Reporting and Data System were assessed clinically using decision curve analysis (DCA).

Results

Multivariate regression showed that irregular shape, elastography score (≥ 3), lack of ring enhancement, and unclear margin after enhancement were independent predictors of malignancy. During the training (area under the ROC [AUC]: 0.936; 95% confidence interval [CI]: 0.902–0.961) and validation (AUC: 0.902; 95% CI: 0.842–0.945) sets, the multimodal US nomogram with these four variables demonstrated good calibration and discrimination. The DCA results confirmed the good clinical applicability of the multimodal US nomogram for predicting thyroid cancer.

Conclusions

As a preoperative prediction tool, our multimodal US-based nomogram showed good ability to distinguish benign from malignant thyroid nodules.